---
title: "Nvidia releases Nemotron 3.5 Super VL, an open 120-billion-parameter vision model, with a new Indic-language dataset"
url: https://anawords.com/story/nvidia-nemotron-3-5-super-vl-open-model-indic-languages
published: 2026-10-16T13:37:48+05:30
updated: 2026-10-16T13:37:48+05:30
section: Open Source AI
author: Mayank Sahu
checked: sources checked by AI, approved by editor
version: 1
---

# Nvidia releases Nemotron 3.5 Super VL, an open 120-billion-parameter vision model, with a new Indic-language dataset

The model reads text, images, documents and video and is built to be post-trained for specific business tasks. Nvidia also released about 2.8 trillion tokens of Indic text across 22 languages.

**In short:** Nvidia released Nemotron 3.5 Super VL on 15 October 2026, an open-weight mixture-of-experts model with 120 billion total and 12 billion active parameters that accepts text, images, documents and video. Nvidia also released an Indic dataset of about 2.8 trillion tokens across 22 languages.

## What Nvidia released

Nvidia published Nemotron 3.5 Super VL on 15 October 2026.[^1] It is a mixture-of-experts model with 120 billion total parameters and 12 billion active for each token, using a hybrid design that includes Mamba layers.[^1] It accepts text, images, documents and video.[^1]

Nvidia released base, post-trained and compressed NVFP4 checkpoints, along with training recipes and datasets.[^1][^3] VentureBeat reports the licence, OpenMDW, allows commercial use, fine-tuning and redistribution.[^2]

## Why it matters for India

Nvidia says it added 10 billion Indic-language tokens in continued pretraining and released an Indic dataset of about 2.8 trillion tokens across 22 languages.[^1] That gives developers building for Indian languages a large, openly available training set.

## Where to get it

The weights are on Hugging Face, with access also through ModelScope, OpenRouter and Nvidia NIM.[^1][^3] VentureBeat reports a free, rate-limited Nvidia-hosted API for development, and that production NIM use needs an Nvidia AI Enterprise licence, quoted at $4,500 per GPU per year.[^2]

## What Nvidia claims

- 80.8% on the CharXiv chart-reasoning test, or 84% with a Python tool.[^1]
- More than 600 output tokens a second on agent tasks through a Baseten endpoint.[^1]
- After task-specific post-training, accuracy on a medical insurance claims test rose from about 28% to 72%, against about 38% for Claude Opus 5, VentureBeat reports from Nvidia’s charts.[^2]

VentureBeat notes the comparisons use customised models on narrow tasks, and Nvidia has not published task definitions or sample sizes.[^2]

## Also announced

Nvidia also introduced Nemotron 3.5 Bolt 74B-A9B for local coding and research, and VentureBeat reports a smaller Bolt E4B model for voice and device agents is due on 23 October.[^2]

## Fact ledger

- [Confirmed] Nemotron 3.5 Super VL has 120 billion total and 12 billion active parameters. (source 1,3)
- [Confirmed] Weights are open, with base, post-trained and NVFP4 checkpoints. (source 1,3)
- [Confirmed] Nvidia released an Indic dataset of about 2.8 trillion tokens across 22 languages. (source 1)
- [Company claim] 80.8% on CharXiv. (source 1)
- [Company claim] Post-trained, it beat Claude Opus 5 on a medical insurance claims test. (source 2)
- [Unconfirmed] Nemotron 3.5 Bolt E4B releases on 23 October. (source 2)
- [Not known] The model’s context length.

## Sources

1. [Nvidia Technical Blog: Nemotron 3.5 Super VL](https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/) — official
2. [VentureBeat: Nvidia’s new open Nemotron 3.5 Super VL](https://venturebeat.com/technology/nvidias-new-open-nemotron-3-5-super-vl-with-post-training-beats-claude-opus-5-gpt-6-1-sol-on-specialized-task-benchmarks)
3. [Hugging Face: NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4) — official